OPTS-TTPO: Enhancing Finite-Sample Policy-Gradient Learning with Tree Search
cs.CL, cs.LG
Submitted: 2026-09-30
Updated: 2026-09-30
Terminology
Sources
- Proximal Policy Optimization Algorithms
- On-Policy Policy Gradient Reinforcement Learning Without On-Policy Sampling
- Adaptive Experience Selection for Policy Gradient
- Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
- Adaptive Rollout Allocation for Online Reinforcement Learning with Verifiable Rewards
- TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning
- Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training
- Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement Learning
- TreeRPO: Tree Relative Policy Optimization
- TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling
- Agentic Reinforced Policy Optimization
- Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents
- SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Qwen3 Technical Report
- DAPO: An Open-Source LLM Reinforcement Learning System at Scale
- REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization
- Measuring Mathematical Problem Solving With the MATH Dataset
- High-Dimensional Continuous Control Using Generalized Advantage Estimation
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering